Learning to Detect Roads in High-Resolution Aerial Images

Reliably extracting information from aerial imagery is a difficult problem with many practical applications. One specific case of this problem is the task of automatically detecting roads. This task is a difficult vision problem because of occlusions, shadows, and a wide variety of non-road objects. Despite 30 years of work on automatic road detection, no automatic or semi-automatic road detection system is currently on the market and no published method has been shown to work reliably on large datasets of urban imagery. We propose detecting roads using a neural network with millions of trainable weights which looks at a much larger context than was used in previous attempts at learning the task. The network is trained on massive amounts of data using a consumer GPU. We demonstrate that predictive performance can be substantially improved by initializing the feature detectors using recently developed unsupervised learning methods as well as by taking advantage of the local spatial coherence of the output labels.We show that our method works reliably on two challenging urban datasets that are an order of magnitude larger than what was used to evaluate previous approaches.

[1]  Ruzena Bajcsy,et al.  Computer Recognition of Roads from Satellite Pictures , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  J. E. Boggess Identification of Roads in Satellite Imagery Using Artificial Neural Networks: A Contextual Approach , 1993 .

[3]  Donald Geman,et al.  An Active Testing Model for Tracking Roads in Satellite Images , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  S. K. Parui,et al.  An improved backpropagation neural network for detection of road-like features in satellite imagery , 1997 .

[5]  Christian Heipke,et al.  EMPIRICAL EVALUATION OF AUTOMATICALLY EXTRACTED ROAD AXES , 1998 .

[6]  Kevin W. Bowyer,et al.  Empirical evaluation techniques in computer vision , 1998 .

[7]  Ivan Laptev,et al.  Automatic extraction of roads from aerial images based on scale space and snakes , 2000 .

[8]  Geoffrey E. Hinton Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[9]  Miguel Á. Carreira-Perpiñán,et al.  Multiscale conditional random fields for image labeling , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[10]  Emmanuel P. Baltsavias,et al.  Object extraction and revision by image analysis using existing geodata and knowledge: current status and steps towards operational systems☆ , 2004 .

[11]  José A. Malpica,et al.  An automatic method for road extraction in rural and semi-urban areas starting from high resolution satellite imagery , 2005, Pattern Recognit. Lett..

[12]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[13]  Zhuowen Tu,et al.  Supervised Learning of Edges and Object Boundaries , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[14]  Peter Wonka,et al.  Road Network Extraction and Intersection Detection From Aerial Images by Tracking Road Footprints , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Mehdi Mokhtarzade,et al.  Road detection from high-resolution satellite images using artificial neural networks , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[16]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[17]  Jake Porway,et al.  A hierarchical and contextual model for aerial image understanding , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  H. Sebastian Seung,et al.  Natural Image Denoising with Convolutional Networks , 2008, NIPS.

[19]  Helmut Mayer,et al.  Object extraction in photogrammetric computer vision , 2008 .

[20]  Ting Peng,et al.  An Extended Phase Field Higher-Order Active Contour Model for Networks and Its Application to Road Network Extraction from VHR Satellite Images , 2008, ECCV.

[21]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[22]  Volodymyr Mnih,et al.  CUDAMat: a CUDA-based matrix class for Python , 2009 .

[23]  Xin Huang,et al.  Road centreline extraction from high‐resolution imagery based on multiscale structural features and support vector machines , 2009 .

[24]  Mohammad Norouzi,et al.  Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning , 2009, CVPR.

[25]  Ting Peng,et al.  Extended Phase Field Higher-Order Active Contour Models for Networks , 2009, International Journal of Computer Vision.

[26]  Geoffrey E. Hinton,et al.  Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images , 2010, AISTATS.